{"id":51088954,"url":"https://github.com/EvoMap/awesome-agent-swarm","last_synced_at":"2026-07-12T04:00:48.103Z","repository":{"id":349571605,"uuid":"1202930050","full_name":"EvoMap/awesome-agent-swarm","owner":"EvoMap","description":"A curated list of AI Agent Swarm frameworks, multi-agent orchestration, swarm intelligence, and collaborative agent systems.","archived":false,"fork":false,"pushed_at":"2026-06-24T09:34:38.000Z","size":324,"stargazers_count":30,"open_issues_count":4,"forks_count":5,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-28T09:03:42.733Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EvoMap.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-06T14:48:18.000Z","updated_at":"2026-06-24T09:34:42.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/EvoMap/awesome-agent-swarm","commit_stats":null,"previous_names":["evomap/awesome-agent-swarm"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/EvoMap/awesome-agent-swarm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvoMap%2Fawesome-agent-swarm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvoMap%2Fawesome-agent-swarm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvoMap%2Fawesome-agent-swarm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvoMap%2Fawesome-agent-swarm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EvoMap","download_url":"https://codeload.github.com/EvoMap/awesome-agent-swarm/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EvoMap%2Fawesome-agent-swarm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35381310,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-12T02:00:06.386Z","response_time":87,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-24T00:00:46.380Z","updated_at":"2026-07-12T04:00:48.079Z","avatar_url":"https://github.com/EvoMap.png","language":"JavaScript","funding_links":[],"categories":["Footnotes"],"sub_categories":["Embodied AI and Robotics"],"readme":"# Awesome Agent Swarm [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n\u003e Multi-agent swarm systems, orchestration frameworks, swarm intelligence, agent communication protocols, and collaborative AI.\n\n## Contents\n\n- [Taxonomy](#taxonomy)\n- [Swarm Frameworks](#swarm-frameworks)\n- [Orchestration and Workflow](#orchestration-and-workflow)\n- [Agent Communication and Protocols](#agent-communication-and-protocols)\n- [Swarm Intelligence](#swarm-intelligence)\n- [Role-Based Agent Teams](#role-based-agent-teams)\n- [Task Decomposition and Planning](#task-decomposition-and-planning)\n- [Swarm Coding and Engineering](#swarm-coding-and-engineering)\n- [Safety and Governance](#safety-and-governance)\n- [Key Research Papers](#key-research-papers)\n- [Benchmarks and Evaluation](#benchmarks-and-evaluation)\n- [Community and Resources](#community-and-resources)\n\n## Taxonomy\n\n```mermaid\ngraph LR\n    Root[\"Agent Swarm\"] --\u003e Core[\"Core\u003cbr/\u003eFrameworks\"]\n    Root --\u003e Coordination[\"Coordination\u003cbr/\u003e\u0026 Communication\"]\n    Root --\u003e Patterns[\"Swarm\u003cbr/\u003ePatterns\"]\n    Root --\u003e Applications[\"Applications\u003cbr/\u003e\u0026 Safety\"]\n\n    Core --\u003e Frameworks[\"Swarm\u003cbr/\u003eFrameworks\"]\n    Core --\u003e Orchestration[\"Orchestration\u003cbr/\u003e\u0026 Workflow\"]\n\n    Coordination --\u003e Protocols[\"A2A \u0026 MCP\u003cbr/\u003eProtocols\"]\n    Coordination --\u003e TaskDecomp[\"Task Decomposition\u003cbr/\u003e\u0026 Planning\"]\n\n    Patterns --\u003e Intelligence[\"Swarm\u003cbr/\u003eIntelligence\"]\n    Patterns --\u003e RoleTeams[\"Role-Based\u003cbr/\u003eAgent Teams\"]\n\n    Applications --\u003e Coding[\"Swarm Coding\u003cbr/\u003e\u0026 Engineering\"]\n    Applications --\u003e Safety[\"Safety \u0026\u003cbr/\u003eGovernance\"]\n```\n\n## Swarm Frameworks\n\nCore frameworks for building and managing multi-agent swarm systems.\n\n\u003c!-- AUTOGEN:frameworks --\u003e\n- [**AutoGen**](https://github.com/microsoft/autogen) - Programming framework for agentic AI by Microsoft. Build multi-agent applications with conversational patterns and group chat. by [@microsoft](https://github.com/microsoft) (59,573 stars)\n- [**OpenAI Agents Python**](https://github.com/openai/openai-agents-python) - Production-ready multi-agent framework from OpenAI. Features agent handoffs, guardrails, and tracing for swarm workflows. by [@OpenAI](https://github.com/OpenAI) (27,730 stars)\n- [**AgentScope**](https://github.com/agentscope-ai/agentscope) - Production-ready multi-agent framework with ReAct, memory, planning, and A2A support. Build and run agents you can see, understand and trust. by [@agentscope-ai](https://github.com/agentscope-ai) (27,568 stars)\n- [**Mastra**](https://github.com/mastra-ai/mastra) - TypeScript framework for building AI-powered multi-agent applications. From the team behind Gatsby. by [@mastra-ai](https://github.com/mastra-ai) (25,935 stars)\n- [**Swarm (OpenAI)**](https://github.com/openai/swarm) - Educational framework exploring lightweight multi-agent orchestration. Demonstrates handoffs and routines patterns for agent coordination. by [@OpenAI](https://github.com/OpenAI) (21,773 stars)\n- [**Google ADK**](https://github.com/google/adk-python) - Open-source Python toolkit by Google for building, evaluating, and deploying multi-agent systems with orchestration support. by [@google](https://github.com/google) (20,518 stars)\n- [**eliza**](https://github.com/elizaOS/eliza) - Autonomous agent framework for building and deploying multi-agent swarms with personality-driven interactions. by [@elizaOS](https://github.com/elizaOS) (18,713 stars)\n- [**Microsoft Agent Framework**](https://github.com/microsoft/agent-framework) - Framework for building, orchestrating and deploying multi-agent systems with support for Python and .NET. by [@microsoft](https://github.com/microsoft) (11,942 stars)\n- [**Spring AI Alibaba**](https://github.com/alibaba/spring-ai-alibaba) - Enterprise-grade multi-agent framework for Java developers by Alibaba. Spring ecosystem integration with agent orchestration. by [@alibaba](https://github.com/alibaba) (10,253 stars)\n- [**EvoMap**](https://github.com/EvoMap/evolver) - Agent Swarm platform with task decomposition, Worker Pool orchestration, Evolution Circles, AI Council multi-agent governance, Privacy Computing, and ARC-AGI-2 arena. by [@EvoMap](https://github.com/EvoMap) (8,872 stars)\n- [**PraisonAI**](https://github.com/MervinPraison/PraisonAI) - Low-code multi-agent framework with 100+ built-in tools. Define agent swarms via YAML configuration. by [@MervinPraison](https://github.com/MervinPraison) (8,360 stars)\n- [**Swarms**](https://github.com/kyegomez/swarms) - Enterprise-grade multi-agent orchestration framework. Sequential, parallel, hierarchical, and mesh swarm topologies. by [@kyegomez](https://github.com/kyegomez) (6,926 stars)\n- [**ROMA**](https://github.com/sentient-agi/ROMA) - Recursive Open Meta-Agent framework to build high-performance multi-agent applications with composable architecture. by [@sentient-agi](https://github.com/sentient-agi) (5,084 stars)\n- [**solace-agent-mesh**](https://github.com/SolaceLabs/solace-agent-mesh) - Event-driven framework for building and orchestrating multi-agent AI systems with seamless integration. by [@SolaceLabs](https://github.com/SolaceLabs) (4,965 stars)\n- [**Agency Swarm**](https://github.com/VRSEN/agency-swarm) - Multi-agent orchestration framework built on OpenAI Agents SDK. Define agent teams with customizable roles and communication flows. by [@VRSEN](https://github.com/VRSEN) (4,477 stars)\n- [**LazyLLM**](https://github.com/LazyAGI/LazyLLM) - Easiest and laziest way for building multi-agent LLM applications with minimal boilerplate. by [@LazyAGI](https://github.com/LazyAGI) (3,856 stars)\n- [**DeepResearchAgent**](https://github.com/SkyworkAI/DeepResearchAgent) - Hierarchical multi-agent system for deep research tasks with adaptive planning and tool integration. by [@SkyworkAI](https://github.com/SkyworkAI) (3,487 stars)\n- [**openai-agents-js**](https://github.com/openai/openai-agents-js) - Lightweight JavaScript framework for multi-agent workflows and voice agents by OpenAI. by [@openai](https://github.com/openai) (3,347 stars)\n- [**BotSharp**](https://github.com/SciSharp/BotSharp) - AI multi-agent framework in .NET for building enterprise conversational agent systems. by [@SciSharp](https://github.com/SciSharp) (3,083 stars)\n- [**trpc-agent-go**](https://github.com/trpc-group/trpc-agent-go) - Go framework for production multi-agent systems with graph workflows, tools, memory, and built-in A2A and MCP support. by [@trpc-group](https://github.com/trpc-group) (1,521 stars)\n\u003c!-- /AUTOGEN:frameworks --\u003e\n\n## Orchestration and Workflow\n\nOrchestration engines, workflow builders, and pipeline frameworks for coordinating agent swarms.\n\n\u003c!-- AUTOGEN:orchestration --\u003e\n- [**Dify**](https://github.com/langgenius/dify) - Production-ready platform for agentic workflow development. Visual workflow builder with multi-agent orchestration, RAG pipeline, and model management. by [@langgenius](https://github.com/langgenius) (148,141 stars)\n- [**DeerFlow**](https://github.com/bytedance/deer-flow) - Open-source long-horizon SuperAgent harness by ByteDance. Multi-agent collaboration for research, coding, and content creation. by [@bytedance](https://github.com/bytedance) (76,434 stars)\n- [**LangGraph**](https://github.com/langchain-ai/langgraph) - Build resilient language agents as graphs. Low-level orchestration framework for stateful, multi-actor applications with durable execution. by [@langchain-ai](https://github.com/langchain-ai) (36,777 stars)\n- [**Conductor**](https://github.com/conductor-oss/conductor) - Event-driven agentic workflow engine providing durable, highly resilient orchestration for applications and AI agent pipelines. by [@conductor-oss](https://github.com/conductor-oss) (32,001 stars)\n- [**FastGPT**](https://github.com/labring/FastGPT) - Knowledge-based platform built on LLMs with comprehensive out-of-the-box data processing and workflow orchestration. by [@labring](https://github.com/labring) (28,865 stars)\n- [**haystack**](https://github.com/deepset-ai/haystack) - Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. by [@deepset-ai](https://github.com/deepset-ai) (25,848 stars)\n- [**trigger.dev**](https://github.com/triggerdotdev/trigger.dev) - Build and deploy fully managed AI agents and multi-agent workflows with durable execution. by [@triggerdotdev](https://github.com/triggerdotdev) (15,601 stars)\n- [**astron-agent**](https://github.com/iflytek/astron-agent) - Enterprise-grade, commercial-friendly agentic workflow platform by iFlytek for building next-generation SuperAgents. by [@iflytek](https://github.com/iflytek) (8,613 stars)\n- [**Agent Squad**](https://github.com/2FastLabs/agent-squad) - AWS framework for managing multiple AI agents and handling complex conversations with intelligent routing. by [@2FastLabs](https://github.com/2FastLabs) (7,687 stars)\n- [**Hatchet**](https://github.com/hatchet-dev/hatchet) - Orchestration engine for background tasks, AI agents, and durable workflows. Queues, scheduling, and durable execution for agent pipelines. by [@hatchet-dev](https://github.com/hatchet-dev) (7,478 stars)\n\u003c!-- /AUTOGEN:orchestration --\u003e\n\n## Agent Communication and Protocols\n\nStandards and protocols for inter-agent messaging, discovery, and interoperability.\n\n\u003c!-- AUTOGEN:communication --\u003e\n- [**A2A**](https://github.com/a2aproject/A2A) - Agent2Agent open protocol by Google enabling communication and interoperability between opaque agent systems. by [@a2aproject](https://github.com/a2aproject) (24,686 stars)\n- [**mcp-use**](https://github.com/mcp-use/mcp-use) - Fullstack MCP framework to develop MCP applications for ChatGPT, Claude, and AI agents. by [@mcp-use](https://github.com/mcp-use) (10,266 stars)\n- [**fastmcp**](https://github.com/punkpeye/fastmcp) - TypeScript framework for building MCP servers with minimal setup. by [@punkpeye](https://github.com/punkpeye) (3,217 stars)\n- [**AgentNetworkProtocol**](https://github.com/agent-network-protocol/AgentNetworkProtocol) - Open source protocol for agent communication with discovery, routing, and cross-network interoperability. by [@agent-network-protocol](https://github.com/agent-network-protocol) (1,344 stars)\n- [**arcade-mcp**](https://github.com/ArcadeAI/arcade-mcp) - MCP server framework and tool-development library for building custom agent capabilities and authenticated tool calls. by [@ArcadeAI](https://github.com/ArcadeAI) (952 stars)\n- [**A2A x402**](https://github.com/google-agentic-commerce/a2a-x402) - A2A protocol extension adding x402 on-chain payments, letting agents monetize services over Agent-to-Agent calls. by [@google-agentic-commerce](https://github.com/google-agentic-commerce) (535 stars)\n- [**Coral Anemoi**](https://github.com/Coral-Protocol/Anemoi) - Semi-centralized multi-agent coordination via Agent-to-Agent Communication MCP server. Enables cross-framework agent collaboration. by [@Coral-Protocol](https://github.com/Coral-Protocol) (370 stars)\n- [**GEP MCP Server**](https://github.com/EvoMap/gep-mcp-server) - MCP Server for Genome Evolution Protocol. Exposes swarm evolution tools to Claude Desktop, Cursor, and any MCP client. by [@EvoMap](https://github.com/EvoMap) (5 stars)\n\u003c!-- /AUTOGEN:communication --\u003e\n\n## Swarm Intelligence\n\nEmergent behavior, collective reasoning, and self-organizing multi-agent systems.\n\n\u003c!-- AUTOGEN:intelligence --\u003e\n- [**TradingAgents**](https://github.com/TauricResearch/TradingAgents) - Multi-agent LLM financial trading framework with fund manager, analyst, and risk advisor roles. by [@TauricResearch](https://github.com/TauricResearch) (91,740 stars)\n- [**OWL**](https://github.com/camel-ai/owl) - Optimized Workforce Learning framework built on CAMEL-AI. #1 on GAIA benchmark (69.09) among open-source multi-agent systems for real-world task automation. by [@camel-ai](https://github.com/camel-ai) (19,927 stars)\n- [**CAMEL**](https://github.com/camel-ai/camel) - The first multi-agent framework. Finding the Scaling Law of Agents through role-playing and communicative agent collaboration. by [@camel-ai](https://github.com/camel-ai) (17,343 stars)\n- [**ClawTeam**](https://github.com/HKUDS/ClawTeam) - Agent Swarm Intelligence framework. Agents self-organize into collaborative teams with dynamic task allocation, inter-agent messaging, and git worktree isolation. by [@HKUDS](https://github.com/HKUDS) (5,364 stars)\n- [**LatentMAS**](https://github.com/Gen-Verse/LatentMAS) - Latent collaboration in multi-agent systems. Agents reason and collaborate in continuous latent space instead of natural language, reducing communication overhead. by [@Gen-Verse](https://github.com/Gen-Verse) (1,035 stars)\n\u003c!-- /AUTOGEN:intelligence --\u003e\n\n## Role-Based Agent Teams\n\nFrameworks that organize agents into specialized roles for collaborative task execution.\n\n\u003c!-- AUTOGEN:role-teams --\u003e\n- [**MetaGPT**](https://github.com/FoundationAgents/MetaGPT) - Virtual software company via multi-agent collaboration. SOPs encoded as prompts assign PM, architect, developer, and QA roles. by [@FoundationAgents](https://github.com/FoundationAgents) (69,260 stars)\n- [**CrewAI**](https://github.com/crewAIInc/crewAI) - Framework for orchestrating role-playing, autonomous AI agents. Define crews with specialized roles, goals, and backstories for collaborative tasks. by [@crewAIInc](https://github.com/crewAIInc) (55,132 stars)\n- [**ChatDev**](https://github.com/OpenBMB/ChatDev) - Virtual software company via LLM-powered multi-agent conversation chains. Agents play CEO, CTO, programmer, and tester roles. by [@OpenBMB](https://github.com/OpenBMB) (33,688 stars)\n- [**HiClaw**](https://github.com/agentscope-ai/HiClaw) - Collaborative Multi-Agent OS with Manager-Workers architecture. Human-in-the-loop task coordination with enterprise-grade security. by [@agentscope-ai](https://github.com/agentscope-ai) (5,019 stars)\n\u003c!-- /AUTOGEN:role-teams --\u003e\n\n## Task Decomposition and Planning\n\nSystems for breaking complex goals into subtasks, building execution DAGs, and coordinating parallel agent work.\n\n\u003c!-- AUTOGEN:task-decomposition --\u003e\n- [**deepagents**](https://github.com/langchain-ai/deepagents) - Agent harness built with LangChain and LangGraph with planning, filesystem backend, and multi-agent collaboration. by [@langchain-ai](https://github.com/langchain-ai) (25,916 stars)\n- [**agent-orchestrator**](https://github.com/AgentWrapper/agent-orchestrator) - Agentic orchestrator for parallel coding agents with task planning, agent spawning, and autonomous handoffs. by [@AgentWrapper](https://github.com/AgentWrapper) (8,125 stars)\n- [**MindSearch**](https://github.com/InternLM/MindSearch) - Multi-agent web search engine. Decomposes search queries into sub-tasks, delegates to specialized agents, and aggregates results. by [@InternLM](https://github.com/InternLM) (6,885 stars)\n- [**Open Multi-Agent**](https://github.com/open-multi-agent/open-multi-agent) - TypeScript multi-agent orchestration via single runTeam() call. Auto-decomposes goals into task DAGs and runs agents in parallel. by [@open-multi-agent](https://github.com/open-multi-agent) (6,536 stars)\n- [**AFlow**](https://github.com/FoundationAgents/AFlow) - Automated multi-agent workflow generation via Monte Carlo tree search. Designs optimal agent topologies for given tasks. by [@geekan](https://github.com/geekan) (547 stars)\n\u003c!-- /AUTOGEN:task-decomposition --\u003e\n\n## Swarm Coding and Engineering\n\nAgent swarms applied to collaborative software development and engineering workflows.\n\n\u003c!-- AUTOGEN:swarm-coding --\u003e\n- [**stagewise**](https://github.com/stagewise-io/stagewise) - Open-source agentic IDE. Create and orchestrate multiple coding agents, preview apps, and run git workflows across model providers. by [@stagewise-io](https://github.com/stagewise-io) (6,719 stars)\n- [**SWE-ReX**](https://github.com/SWE-agent/SWE-ReX) - Sandboxed, massively-parallel code execution runtime for AI agents. Runs many agents locally or in the cloud; powers SWE-agent. by [@SWE-agent](https://github.com/SWE-agent) (545 stars)\n\u003c!-- /AUTOGEN:swarm-coding --\u003e\n\n## Safety and Governance\n\nGuardrails, policy engines, and governance frameworks for multi-agent systems.\n\n\u003c!-- AUTOGEN:safety --\u003e\n- [**NeMo Guardrails**](https://github.com/NVIDIA-NeMo/Guardrails) - NVIDIA's toolkit for adding programmable guardrails to LLM systems. Policy-based safety controls for multi-agent deployments. by [@NVIDIA-NeMo](https://github.com/NVIDIA-NeMo) (6,634 stars)\n\u003c!-- /AUTOGEN:safety --\u003e\n\n## Key Research Papers\n\n### Surveys\n\n- [LLMs Working in Harmony: A Survey on Building Effective LLM-Based Multi Agent Systems](https://arxiv.org/abs/2504.01963) (arXiv'25) - Covers architecture, memory, planning, and frameworks for multi-agent LLM systems.\n- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://arxiv.org/abs/2501.06322) (arXiv'25) - Characterizes collaboration by actors, types (cooperation, competition, coopetition), structures, and protocols.\n- [A Comprehensive Survey of Self-Evolving AI Agents](https://arxiv.org/abs/2508.07407) (arXiv'25) - Taxonomy of single-agent, multi-agent, and domain-specific evolution.\n- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://www.ijcai.org/proceedings/2024/0890.pdf) (IJCAI'24) - Agent profiling, communication methods, and skill development.\n\n### Swarm Orchestration and Architecture\n\n- [AgentOrchestra: A Hierarchical Multi-Agent Framework for General-Purpose Task Solving](https://arxiv.org/abs/2506.12508) (arXiv'25) - Conductor-inspired hierarchical framework with MCP Manager Agent. 83.39% on GAIA benchmark.\n- [MAS-Orchestra: Understanding Multi-Agent Reasoning Through Holistic Orchestration](https://arxiv.org/abs/2601.14652) (arXiv'26) - Multi-agent orchestration as a function-calling RL problem. Introduces MASBENCH along 5 dimensions.\n- [AdaptOrch: Task-Adaptive Orchestration](https://arxiv.org/abs/2602.16873) (arXiv'26) - Dynamic topology selection (parallel, sequential, hierarchical, hybrid) based on task dependency graphs. 12-23% over static baselines.\n- [Puppeteer: Evolving Orchestration via Reinforcement Learning](https://arxiv.org/abs/2505.19591) (arXiv'25) - Centralized orchestrator trained via RL to dynamically direct agents in response to evolving task states.\n\n### Swarm Intelligence and Emergence\n\n- [SwarmSys: Decentralized Swarm-Inspired Agents for Scalable Reasoning](https://arxiv.org/abs/2510.10047) (arXiv'25) - Explorers, Workers, and Validators with pheromone-inspired reinforcement. Coordination scaling vs model scaling.\n- [SIER: Swarm Intelligence Enhancing Reasoning](https://arxiv.org/abs/2505.17115) (arXiv'25) - Kernel density estimation and non-dominated sorting for swarm-guided LLM reasoning.\n- [Multi-Agent Systems Powered by LLMs: Applications in Swarm Intelligence](https://arxiv.org/abs/2503.03800) (arXiv'25) - LLMs integrated into multi-agent simulations for ant colony foraging and bird flocking.\n- [LatentMAS: Latent Collaboration in Multi-Agent Systems](https://arxiv.org/abs/2506.06637) (arXiv'25) - Agents collaborate in continuous latent space instead of natural language.\n- [GPTSwarm: Language Agents as Optimizable Graphs](https://arxiv.org/abs/2402.16823) (ICML'24) - Graph-based optimization of agent collaboration topologies.\n- [Scaling Large-Language-Model-based Multi-Agent Collaboration](https://arxiv.org/abs/2406.07155) (arXiv'24) - Scaling laws and topology analysis for multi-agent collaboration.\n\n### Multi-Agent Collaboration and Evolution\n\n- [Self-Evolving Multi-Agent Collaboration Networks](https://arxiv.org/abs/2410.02849) (ICLR'25) - Multi-agent systems that evolve their collaboration patterns through experience.\n- [AFlow: Automating Agentic Workflow Generation](https://arxiv.org/abs/2410.10762) (ICLR'25) - Monte Carlo tree search for automated multi-agent workflow design.\n- [Automated Design of Agentic Systems (ADAS)](https://arxiv.org/abs/2408.08435) (ICLR'25) - Meta-learning for automatic agent system design.\n- [AgentVerse: Facilitating Multi-Agent Collaboration](https://arxiv.org/abs/2308.10848) (ICLR'24) - Emergent behaviors in multi-agent environments.\n- [SEMAG: Self-Evolutionary Multi-Agent Code Generation](https://arxiv.org/abs/2603.15707) (arXiv'26) - Self-evolutionary agents that auto-upgrade backbone models.\n- [SAGE: Multi-Agent Self-Evolution for LLM Reasoning](https://arxiv.org/abs/2603.15255) (arXiv'26) - Four co-evolving agents from shared LLM backbone.\n- [Group-Evolving Agents](https://arxiv.org/abs/2602.04837) (arXiv'26) - Agent groups as evolutionary units with experience sharing. 71.0% on SWE-bench Verified.\n- [CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://arxiv.org/abs/2604.01658) (arXiv'26) - First framework for autonomous multi-agent evolution on open-ended problems. Persistent memory, asynchronous execution, and heartbeat-based interventions. 3-10x improvement over fixed baselines.\n\n### Role-Based Teams and Software Engineering\n\n- [MetaGPT: Meta Programming for Multi-Agent Collaboration](https://arxiv.org/abs/2308.00352) (ICLR'24) - SOPs encoded as prompts for multi-agent software development.\n- [Communicative Agents for Software Development](https://arxiv.org/abs/2307.07924) (ACL'24) - ChatDev: virtual software company through multi-agent conversation chains.\n- [Agyn: Team-Based Autonomous Software Engineering](https://arxiv.org/abs/2602.01465) (arXiv'26) - Coordination, research, implementation, and review agents. 72.2% on SWE-bench 500.\n- [Self-Organizing Multi-Agent Systems for Continuous Software Development](https://arxiv.org/abs/2603.25928) (arXiv'26) - Manager agents dynamically hire/assign/fire workers. Multi-day continuous development.\n- [AgentMesh: Cooperative Multi-Agent Framework for Software Development](https://arxiv.org/abs/2507.19902) (arXiv'25) - Planner, Coder, Debugger, Reviewer agents for end-to-end development.\n- [MoRAgent: Parameter Efficient Agent Tuning with Mixture-of-Roles](https://arxiv.org/abs/2512.21708) (arXiv'25) - Reasoner, executor, and summarizer roles via specialized LoRA groups.\n\n### Task Decomposition and Planning\n\n- [Modular Task Decomposition and Dynamic Collaboration in Multi-Agent Systems](https://arxiv.org/abs/2511.01149) (arXiv'25) - Hierarchical sub-task decomposition with dynamic scheduling and constraint parsing.\n- [CodeAgents: Token-Efficient Multi-Agent Reasoning](https://arxiv.org/abs/2507.03254) (arXiv'25) - Multi-agent reasoning codified into modular pseudocode. 55-87% token reduction.\n- [ReWOO: Decoupling Reasoning from Observations](https://arxiv.org/abs/2305.18323) (ICML'24) - Efficient tool-augmented reasoning by decoupling planning from execution.\n- [Tree of Thoughts: Deliberate Problem Solving with LLMs](https://arxiv.org/abs/2305.10601) (NeurIPS'23) - Tree-structured reasoning for complex problem solving.\n- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends](https://arxiv.org/abs/2303.17580) (NeurIPS'23) - Task decomposition across specialized AI models.\n\n### Agent Communication Protocols\n\n- [Agent Communication Protocol (ACP)](https://arxiv.org/abs/2602.15055) (arXiv'26) - Standardized A2A framework with federated orchestration, semantic intent mapping, and zero-trust security. 40% latency reduction.\n- [AgentMaster: Multi-Agent Framework Using A2A and MCP](https://arxiv.org/abs/2507.21105) (EMNLP'25) - Combined A2A and MCP protocols for multimodal information retrieval. BERTScore F1 96.3%.\n- [Critical Analysis of A2A and MCP Integration for Scalable Agent Systems](https://arxiv.org/abs/2505.03864) (arXiv'25) - Semantic interoperability, security, and governance challenges in A2A+MCP integration.\n\n### Safety, Governance, and Alignment\n\n- [AGENTSAFE: Unified Framework for Ethical Assurance and Governance in Agentic AI](https://arxiv.org/abs/2512.03180) (arXiv'25) - Design, runtime, and audit controls covering the agentic loop (plan, act, observe, reflect).\n- [MI9: Integrated Runtime Governance Framework for Agentic AI](https://arxiv.org/abs/2508.03858) (arXiv'25) - Agency-risk index, semantic telemetry, conformance engines, and graduated containment.\n- [The Alignment Flywheel: Governance-Centric Hybrid Multi-Agent Architecture](https://arxiv.org/abs/2603.02259) (arXiv'26) - Proposer + Safety Oracle with patch locality for runtime governance.\n- [OpenGuardrails: Context-Aware AI Guardrails Platform](https://arxiv.org/abs/2510.19169) (arXiv'25) - Context-aware safety detection and model-manipulation prevention.\n\n## Benchmarks and Evaluation\n\n- [MultiAgentBench](https://arxiv.org/abs/2503.01935) (arXiv'25) - Evaluates collaboration and competition across star, chain, tree, and graph topologies.\n- [SwarmBench: Benchmarking LLMs' Swarm Intelligence](https://arxiv.org/abs/2505.04364) (arXiv'25) - Pursuit, Synchronization, Foraging, Flocking, Transport tasks under decentralized constraints.\n- [Silo-Bench: Evaluating Distributed Coordination in Multi-Agent LLM Systems](https://arxiv.org/abs/2603.01045) (arXiv'26) - 30 algorithmic tasks across 3 communication complexity levels. Reveals the \"Communication-Reasoning Gap\".\n- [Collab-Overcooked: Evaluating Fine-Grained Collaboration](https://arxiv.org/abs/2503.xxxxx) (EMNLP'25) - Competence boundary awareness, communication, and dynamic adaptation assessment.\n- [MASBENCH: Controlled Benchmark for Multi-Agent Orchestration](https://arxiv.org/abs/2601.14652) (arXiv'26) - Tasks characterized along Depth, Horizon, Breadth, Parallel, and Robustness dimensions.\n- [SWE-bench](https://github.com/princeton-nlp/SWE-bench) (ICLR'24) - Can agent swarms resolve real-world GitHub issues?\n- [AgentBench](https://github.com/THUDM/AgentBench) (ICLR'24) - Multi-dimensional evaluation of LLMs as agents.\n- [GAIA](https://huggingface.co/gaia-benchmark) (ICLR'23) - General AI assistant capabilities benchmark.\n\n## Community and Resources\n\n\u003c!-- AUTOGEN:community --\u003e\n_No projects yet. [Submit one!](https://github.com/EvoMap/awesome-agent-swarm/issues/new?template=project-submission.yml)_\n\u003c!-- /AUTOGEN:community --\u003e\n\n## Footnotes\n\nMaintained by [EvoMap](https://evomap.ai). See [contributing guidelines](contributing.md) for how to submit a project or paper.\n\nAlso check out [Awesome Agent Evolution](https://github.com/EvoMap/awesome-agent-evolution) for agent self-evolution, memory systems, and autonomous self-improvement.\n\n[![Star History Chart](https://api.star-history.com/svg?repos=EvoMap/awesome-agent-swarm,EvoMap/awesome-agent-evolution,EvoMap/evolver,openai/swarm,openai/openai-agents-python,microsoft/autogen,crewAIInc/crewAI,langgenius/dify,FoundationAgents/MetaGPT,langchain-ai/langgraph,kyegomez/swarms,google/A2A,camel-ai/camel,camel-ai/owl,bytedance/deer-flow,HKUDS/ClawTeam\u0026type=Date)](https://star-history.com/#EvoMap/awesome-agent-swarm\u0026openai/swarm\u0026openai/openai-agents-python\u0026microsoft/autogen\u0026crewAIInc/crewAI\u0026langgenius/dify\u0026FoundationAgents/MetaGPT\u0026langchain-ai/langgraph\u0026kyegomez/swarms\u0026google/A2A\u0026camel-ai/camel\u0026camel-ai/owl\u0026bytedance/deer-flow\u0026HKUDS/ClawTeam\u0026Date)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEvoMap%2Fawesome-agent-swarm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEvoMap%2Fawesome-agent-swarm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEvoMap%2Fawesome-agent-swarm/lists"}